Update app.py

app.py

@@ -10,6 +10,7 @@ import torch
 from transformers import AutoModelForCausalLM, AutoTokenizer, TextIteratorStreamer
 
 DESCRIPTION = "# ConvAI 9b"
+hf_token = os.getenv("hf_token")
 
 if not torch.cuda.is_available():
     DESCRIPTION += "\n<p>Running on CPU 🥶 This demo does not work on CPU.</p>"
@@ -20,7 +21,7 @@ MAX_INPUT_TOKEN_LENGTH = int(os.getenv("MAX_INPUT_TOKEN_LENGTH", "4096"))
 
 if torch.cuda.is_available():
     model_id = "CreitinGameplays/ConvAI-9b"
-    model = AutoModelForCausalLM.from_pretrained(model_id, torch_dtype=torch.float16, device_map="auto")
+    model = AutoModelForCausalLM.from_pretrained(model_id, torch_dtype=torch.float16, device_map="auto", auth_token=hf_token)
     tokenizer = AutoTokenizer.from_pretrained(model_id)
 
 @spaces.GPU